Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4152 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.8681. Min Act: -0.1700
Data Index: 1765479 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.7118. Min Act: -0.1700
Data Index: 1177619 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.7431. Min Act: -0.1700
Data Index: 6435227 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.5868. Min Act: -0.1700
Data Index: 5087570 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.4931. Min Act: -0.1700
Data Index: 8042981 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.4306. Min Act: -0.1700
Data Index: 370137 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.4618. Min Act: -0.1700
Data Index: 6881139 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.4306. Min Act: -0.1700
Data Index: 5839480 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.4618. Min Act: -0.1700
Data Index: 1934503 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.4306. Min Act: -0.1700
Data Index: 5306569 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.3681. Min Act: -0.1700
Data Index: 7159696 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.3993. Min Act: -0.1700
Data Index: 386049 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.3681. Min Act: -0.1700
Data Index: 5088681 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.3368. Min Act: -0.1700
Data Index: 189577 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8109909 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.2743. Min Act: -0.1700
Data Index: 4117742 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.3056. Min Act: -0.1700
Data Index: 5095688 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.3056. Min Act: -0.1700
Data Index: 2916645 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.3056. Min Act: -0.1700
Data Index: 4476678 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8681. Min Range: -5.8681
Max Act: 5.2431. Min Act: -0.1700
Data Index: 4225323 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19